Mobile Terminal Real-Time Face Area Image Correction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image correction techniques for mobile terminals often result in significant discrepancies between corrected and original images, and can only be applied to previously stored images, failing to provide efficient and accurate real-time correction of images captured by the camera.

Innovation Solution

A method and mobile terminal implementation that automatically detects and corrects face areas or entire images in real-time using image correction information, allowing for selective correction and display of the corrected image without degrading the original image quality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If existing image correction techniques are applied to correct the entire image, then image quality can be improved, but huge discrepancies occur between the corrected image and the original image

Engineering Contradiction:
Improveimage correction accuracyVSAvoidimage originality
Core Design Contradiction:
Manufacturing precisionVSLoss of information

Solution Approach 1:

The patent segments the image into multiple regions including face regions and non-face regions. Different correction processing is applied to different regions, allowing precise correction of face areas while preserving the original appearance of other parts of the image, thus resolving the contradiction between correction accuracy and image originality

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by performing image correction only on specific regions (face regions) rather than the entire image. This allows high correction accuracy for face areas while maintaining the original characteristics of non-face regions, preventing huge discrepancies between corrected and original images

Inventive Principle:
Principle #3Local quality

2Manufacturing precision

If existing image correction techniques are used, then image correction can be performed, but only on previously stored images and not on images being captured in real-time

Engineering Contradiction:
Improveimage correction capabilityVSAvoidcorrection timing
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary action by detecting face regions and applying correction processing during the image capture process itself, before the image is stored. This eliminates the time delay associated with post-capture correction and enables real-time correction of captured images

Inventive Principle:
Principle #10Preliminary action

3Manufacturing precision

If selective correction of image parts is implemented, then image quality can be improved with minimal change to the original, but the device complexity increases

Engineering Contradiction:
Improveselective correction accuracyVSAvoidprocessing complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent uses segmentation to divide the image into face regions and non-face regions based on predefined criteria. This structured approach to selective correction simplifies the processing complexity while achieving high correction accuracy on specific image parts

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements a universal correction framework that can handle different types of images and regions using the same basic processing logic. The face region detection and correction mechanism serves multiple purposes including quality improvement and originality preservation, reducing overall system complexity

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP2106125B1Mobile terminal and method of controlling the mobile terminal
Publication Date: 2021.05.19 LG ELECTRONICS INC
  • EP2106125B1 patent drawingFigure 1
  • EP2106125B1 patent drawingFigure 2
  • EP2106125B1 patent drawingFigure 3

AI summary

A mobile terminal and a method of controlling a mobile terminal are provided. The method includes displaying a camera preview image; detecting a face area from the camera preview image; if a button for capturing an image is manipulated, correcting an image captured by a camera using the detected face area and displaying the corrected captured image; and storing the corrected captured image.